New Auxiliary Function with Properties in Nonsmooth Global Optimization for Melanoma Skin Cancer Segmentation.
Ontology highlight
ABSTRACT:
SUBMITTER: Masoud Abdulhamid IA
PROVIDER: S-EPMC7178473 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
New Auxiliary Function with Properties in Nonsmooth Global Optimization for Melanoma Skin Cancer Segmentation.
Masoud Abdulhamid Idris A IA Sahiner Ahmet A Rahebi Javad J
BioMed research international 20200413
In this paper, an algorithm is introduced to solve the global optimization problem for melanoma skin cancer segmentation. The algorithm is based on the smoothing of an auxiliary function that is constructed using a known local minimizer and smoothed by utilising Bezier curves. This function achieves all filled function properties. The proposed optimization method is applied to find the threshold values in melanoma skin cancer images. The proposed algorithm is implemented on PH2, ISBI2016 challen ...[more]
Similar Datasets
Project description:Densely labelled segmentation data for digital pathology images is costly to produce but is invaluable to training effective machine learning models. We make available 290 hand-annotated histopathology tissue sections of the 3 most common skin cancers; basal cell carcinoma (BCC), squamous cell carcinoma (SCC) and intraepidermal carcinoma (IEC). These non-melanoma skin cancers constitute over 90% of all skin cancer diagnoses and hence this dataset gives an opportunity to the scientific community to benchmark analytic methodologies on a significant portion of the dermatopathology workflow. The data represents typical cases of the three cancer types (not requiring a differential diagnosis) across shave, punch and excision biopsy contexts. Each image is accompanied with a segmentation mask which characterizes the section into 12 tissue types, specifically: keratin, epidermis, papillary dermis, reticular dermis, hypodermis, inflammation, glands, hair follicles and background, as well as BCC, SCC and IEC. Included also are cancer margin measurements to work towards automated assessment of surgical margin clearance and tumour invasion. This leaves open many opportunities for researchers to utilize or extend the dataset, building upon recent work on image analysis problems in skin cancer (Thomas et al., 2021).
| S-EPMC8627989 | biostudies-literature
Project description:Melanoma is an abnormal proliferation of skin cells that arises and develops in most of the cases on surface of skin that is exposed to copious amounts of sunlight. This common type of cancer may develop in areas of the skin that are not exposed to a much abundant sunlight. The research addresses the problem of Segmentation and Classification of Melanoma Skin Cancer. Melanoma is the fifth most common skin cancer lesion. Bio-medical Imaging and Analysis has become more promising, interesting, and beneficial in recent years to address the eventual problems of Melanoma Skin Cancerous Tissues that may develop on Skin Surfaces. The evolved research finds that Attributes Selected for Classification with Color Layout Filter model. The research has produced an optimal result in terms of certain performance metrics accuracy, precision, recall, PRC (what is PRC? Expansion is needed in Abstract), The proposed method has yielded 90.96% of accuracy and 91% percent of precise and 0.91 of recall out of 1.0, 0.95 of ROC AUC, 0.87 of Kappa Statistic, 0.91 of F-Measure. It has been noticed a lowest error with reference to proposed method on certain dataset. Finally, this research recommends that the Attribute Selected Classifier by implementing one of the image enhancement techniques like Color Layout Filter is showing an efficient outcome.
| S-EPMC10161578 | biostudies-literature
Project description:Advanced melanoma and non-melanoma skin cancers (NMSCs) are burdened with a dismal prognosis. To improve the survival of these patients, studies on immunotherapy and target therapies in melanoma and NMSCs are rapidly increasing. BRAF and MEK inhibitors improve clinical outcomes, and anti-PD1 therapy demonstrates better results than chemotherapy or anti-CTLA4 therapy in terms of the survival of patients with advanced melanoma. In recent years, the combination therapy of nivolumab plus ipilimumab has gained ground in studies for its survival and response rate benefits in patients with advanced melanoma. In addition, neoadjuvant treatment for stages III and IV melanoma, either as monotherapy or combination therapy, has recently been discussed. Another promising strategy evaluated in recent studies is the triple combination of anti-PD-1/PD-L1 immunotherapy and anti-BRAF plus anti-MEK targeted therapy. On the contrary, in advanced and metastatic BCC, successful therapeutic strategies, such as vismodegib and sonidegib, are based on the inhibition of aberrant activation of the Hedgehog signaling pathway. In these patients, anti-PD-1 therapy with cemiplimab should be reserved as the second-line therapy in case of disease progression or poor response. In patients with locally advanced or metastatic SCC, who are not candidates for surgery or radiotherapy, anti-PD1 agents such as cemiplimab, pembrolizumab, and cosibelimab (CK-301) have shown significant results in terms of response rate. PD-1/PD-L1 inhibitors, such as avelumab, have also been used in Merkel carcinoma, achieving responses in half of the patients with advanced disease. The latest prospect emerging for MCC is the locoregional approach involving the injection of drugs that can stimulate the immune system. Two of the most promising molecules used in combination with immunotherapy are cavrotolimod (a Toll-like receptor 9 agonist) and a Toll-like receptor 7/8 agonist. Another area of study is cellular immunotherapy with natural killer cells stimulated with an IL-15 analog or CD4/CD8 cells stimulated with tumor neoantigens. Neoadjuvant treatment with cemiplimab in CSCCs and nivolumab in MCCs has shown promising results. Despite the successes of these new drugs, the new challenges ahead will be to select patients who will benefit from these treatments based on biomarkers and parameters of the tumor microenvironment.
| S-EPMC9947410 | biostudies-literature
Project description:(1) Background: Non-melanoma skin cancer is the most frequently diagnosed cancer in humans. The process of skin carcinogenesis is still not fully understood. However, several studies have been conducted to better explain the mechanisms that lead to malignancy; (2) Methods: We reviewed the more recent literature about the pathogenesis of non-melanoma skin cancer focusing on basal cell carcinomas, squamous cell carcinoma and actinic keratosis; (3) Results: Several papers reported genetic and molecular alterations leading to non-melanoma skin cancer. Plenty of risk factors are involved in non-melanoma skin cancer pathogenesis, including genetic and molecular alterations, immunosuppression, and ultraviolet radiation; (4) Conclusion: Although skin carcinogenesis is still not fully understood, several papers demonstrated that genetic and molecular alterations are involved in this process. In addition, plenty of non-melanoma skin cancer risk factors are now known, allowing for an effective prevention of non-melanoma skin cancer development. Compared to other papers on the same topic, our review focused on molecular and genetic factors and analyzed in detail several factors involved in non-melanoma skin cancer.
| S-EPMC5874663 | biostudies-literature
Project description:Purpose of reviewThe therapeutic landscape for non-melanoma skin cancer (NMSC) has recently expanded with the development of effective and targeted immunotherapy. Here, we provide an overview of the role of immunotherapy in the management of advanced cutaneous carcinomas.Recent findingsSeveral agents were recently U.S. Food and Drug Administration (FDA)-approved for the treatment of locally advanced and metastatic cutaneous squamous cell carcinoma, Merkel cell carcinoma, and basal cell carcinoma. However, recent approvals in tissue-agnostic indications may also benefit other NMSCs including cutaneous adnexal solid tumors with high tumor mutation burdens or microsatellite instability. Furthermore, while FDA-approved indications will likely continue to expand, continued studies are needed to support the role of immunotherapy in the neoadjuvant, adjuvant, and refractory settings. Immunotherapy is emerging as the standard of care for several advanced NMSCs not amenable to surgery and radiation. Ongoing evaluation of the clinical trial landscape is needed to optimize enrollment and ensure continued innovation.
| S-EPMC8395379 | biostudies-literature
Project description:IntroductionSeveral studies have shown an increased risk of cancer after non melanoma skin cancers (NMSC) but the individual risk factors underlying this risk have not been elucidated, especially in relation to sun exposure and skin sensitivity to sunlight.PurposeThe aim of this study was to examine the individual risk factors associated with the development of subsequent cancers after non melanoma skin cancer.MethodsParticipants in the population-based New Hampshire Skin Cancer Study provided detailed risk factor data, and subsequent cancers were identified via linkage with the state cancer registry. Deaths were identified via state and national death records. A Cox proportional hazard model was used to estimate risk of subsequent malignancies in NMSC patients versus controls and to assess the potential confounding effects of multiple risk factors on this risk.ResultsAmong 3584 participants, risk of a subsequent cancer (other than NMSC) was higher after basal cell carcinoma (BCC) (adjusted HR 1.40 [95% CI 1.15, 1.71]) than squamous cell carcinoma (SCC) (adjusted HR 1.18 [95% CI 0.95, 1.46]) compared to controls (adjusted for age, sex and current cigarette smoking). After SCC, risk was higher among those diagnosed before age 60 (HR 1.96 [95% CI 1.24, 3.12]). An over 3-fold risk of melanoma after SCC (HR 3.62; 95% CI 1.85, 7.11) and BCC (HR 3.28; 95% CI 1.66, 6.51) was observed, even after further adjustment for sun exposure-related factors and family history of skin cancer. In men, prostate cancer incidence was higher after BCC compared to controls (HR 1.64; 95% CI 1.10, 2.46).ConclusionsOur population-based study indicates an increased cancer risk after NMSC that cannot be fully explained by known cancer risk factors.
| S-EPMC4061037 | biostudies-literature
Project description:Arsenic exposure may alter the efficiency of DNA repair. UV damage is specifically repaired by nucleotide excision repair (NER), and common genetic variants in NER may increase risk for non-melanoma skin cancer (NMSC).We tested whether polymorphisms in the NER genes XPA (A23G) and XPD (Asp312Asn and Lys751Gln) modify the association between arsenic and NMSC.Incident cases of basal and squamous cell carcinoma (BCC and SCC, respectively) were identified through a network of dermatologists and pathology laboratories across New Hampshire. Population-based controls were frequency matched to cases on age and sex. Arsenic exposure was assessed in toenail clippings. The analysis included 880 cases of BCC, 666 cases of SCC, and 780 controls.There was an increased BCC risk associated with high arsenic exposure among those homozygous variant for XPA [odds ratio (OR) = 1.8; 95% confidence interval (CI), 0.9-3.7]. For XPD, having variation at both loci (312Asn and 751Gln) occurred less frequently among BCC and SCC cases compared with controls (OR = 0.8; 95% CI, 0.6-1.0) for both case groups. In the stratum of subjects who have variant for both XPD polymorphisms, there was a 2-fold increased risk of SCC associated with elevated arsenic (OR = 2.2; 95% CI, 1.0-5.0). The test for interaction between XPD and arsenic in SCC was of borderline significance (p < 0.07, 3 degrees of freedom).Our findings indicate a reduced NMSC risk in relation to XPD Asp312Asn and Lys751Gln variants. Further, these data support the hypothesis that NER polymorphisms may modify the association between NMSC and arsenic.
| S-EPMC1940098 | biostudies-literature
Project description:In typical classification problems, high level concept features provided by a domain expert are usually available during classifier training but not during its deployment. We address this problem from a multitask learning (MTL) perspective by treating these features as auxiliary learning tasks. Previous efforts in MTL have mostly assumed that all tasks have the same input space. However, auxiliary tasks can have different input spaces, since their learning targets are different. Thus, to handle cases with heterogeneous input, in this paper we present a newly developed model using heterogeneous auxiliary tasks to help main task learning. First, we formulate a convex optimization problem for the proposed model, and then, we analyze its hypothesis class and derive true risk bounds. Finally, we compare the proposed model with other relevant methods when applied to the problem of skin cancer screening and public datasets. Our results show that the performance of the proposed method is highly competitive compared to other relevant methods.
| S-EPMC4022611 | biostudies-literature
Project description:Skin cutaneous melanoma (SKCM) is one of the most aggressive and life-threatening cancers with high incidence rate, metastasis rate and mortality. Early detection and stratification of risk assessment are essential to treat SKCM and to improve survival rate. The aim of this study is to construct an immune-related lncRNAs (immlncRNAs) prognosis risk model to identify immune biomarkers for early diagnosis, prognosis assessment and target immunotherapy of SKCM. For this purpose, we identified 46 immlncRNAs significantly correlated with SKCM prognosis to construct the prognostic risk model and patients were stratified into the high- and low-risk subgroups according to the developed model. The predictive efficiency of this model has been proved by K-M survival analysis and receiver operating characteristic curve. Moreover, CIBERSORT algorithms confirmed that there were differences in immune cell infiltration between the high- and low-risk groups. Functional enrichment analysis further indicated that immlncRNAs were related to a variety of immune response process signaling pathways, suggesting that relevant immlncRNAs could play an important role in the immune regulation of SKCM. Finally, subgroup analysis and multiple Cox regression analysis further proved the stability of the model. In summary, we successfully constructed a 46 immlncRNA-related prognostic risk score model with excellent predictive efficacy and provided more possibilities to investigate the immune regulation mechanisms and to develop immunotherapy of SKCM.
| S-EPMC9037265 | biostudies-literature
Project description:Mitochondrial DNA (mtDNA) damage, predominantly encompassing point mutations, has been reported in a variety of cancers. Here we present in human skin, the first detailed study of the distribution of multiple forms of mtDNA damage in nonmelanoma skin cancer (NMSC) compared to histologically normal perilesional dermis and epidermis. We present the first entire spectrum of deletions found between different types of skin tumours and perilesional skin. In addition, we provide the first quantitative data for the incidence of the common deletion as well as the first report of specific tandem duplications in tumours from any tissue. Importantly, this work shows that there are clear differences in the distribution of deletions between the tumour and the histologically normal perilesional skin. Furthermore, DNA sequencing of four mutation 'hotspot' regions of the mitochondrial genome identified a previously unreported somatic heteroplasmic mutation in an SCC patient. In addition, 81 unreported and reported homoplasmic single base changes were identified in the other NMSC patients. Unlike the distribution of deletions and the heteroplasmic mutation, these homoplasmic mutations were present in both tumour and perilesional skin, which suggests that for some genetic studies the traditional use of histologically normal perilesional skin from NMSC patients may be limited. Currently, it is unclear whether mtDNA damage has a direct link to skin cancer or it may simply reflect an underlying nuclear DNA instability.
| S-EPMC2376793 | biostudies-other